Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1906912 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1789726 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.1039. Min Act: -0.0000

Data Index: 384800 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1964500 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0394. Min Act: -0.0000

Data Index: 439314 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9916. Min Act: -0.0000

Data Index: 317812 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0637. Min Act: -0.0000

Data Index: 586776 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0280. Min Act: -0.0000

Data Index: 657385 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0020. Min Act: -0.0000

Data Index: 227894 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1921757 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9689. Min Act: -0.0000

Data Index: 402610 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1346415 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0268. Min Act: -0.0000

Data Index: 573821 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0201. Min Act: -0.0000

Data Index: 866595 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1010583 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.1039. Min Range: -1.1039

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1136922 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.8747. Min Act: -0.0000

Data Index: 744819 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9157. Min Act: -0.0000

Data Index: 546650 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1884994 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.1039. Min Range: -1.1039

Max Act: 0.9295. Min Act: -0.0000

Data Index: 157744 (The Pile)

Max Activating Token Index: 410